AgentIndex icon
AgentIndex
AgentRecall-MCP logo
AgentRecall-MCP
★ 371
vs
remindb logo
remindb
★ 129

AgentRecall-MCP vs remindb

AgentRecall-MCP: AgentRecall is a learning loop for AI agents that provides persistent, compounding memory. It captures corrections automatically, surfaces past insights across projects, and uses a five-layer memory pyramid with Ebbinghaus decay and Bayesian feedback. Zero cloud, all local markdown files.; remindb: remindb stores agentic memory in a single SQLite file. It parses notes into a structured tree with temperature tracking, enables efficient retrieval via FTS5 search, and supports versioning and summarization. This reduces token costs compared to re-reading raw files every session.

01

TL;DR

AgentRecall-MCP logo
AgentRecall-MCPMemory & Context · ★ 371

Maintain context across AI agent sessions (Claude Code, Cursor, etc.)

Read AgentRecall-MCP full review →
remindb logo
remindbMemory & Context · ★ 129

Prevent coding agents from re-reading the same notes every session

Read remindb full review →
02

Side-by-Side Comparison

Field
AgentRecall-MCP logoAgentRecall-MCP
remindb logoremindb
Category
Memory & Context
Memory & Context
Stars
★ 371
★ 129
License
MIT
MIT
Install Command
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
curl -fsSL https://raw.githubusercontent.com/radimsem/remindb/main/install.sh | bash
Updated
1w ago
2mo ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai-agents, claude-code
agent-memory, ai-agents, ast
03

Features

AgentRecall-MCP logoAgentRecall-MCP
01Persistent, compounding memory with 200-line awareness cap
02Automatic correction capture and alignment checking
03Cross-project insight recall via keyword and semantic (pgvector) search
04Zero cloud, all local markdown files, Obsidian-compatible
0510 MCP tools for agents, plus SDK and CLI
remindb logoremindb
01Structured memory tree with typed nodes (heading, list, code, etc.)
02Temperature mechanism that tracks node usage and promotes hot content
03Automatic summarization of cold nodes via agent-driven compaction
04Git-style versioning with per-node diffs and snapshot cursors
05Full-text search (FTS5) with token budget control
04

Use Cases

AgentRecall-MCP logoAgentRecall-MCP
↳Maintain context across AI agent sessions (Claude Code, Cursor, etc.)
↳Capture and learn from user corrections in software development
↳Coordinate memory across multiple parallel agents
remindb logoremindb
↳Prevent coding agents from re-reading the same notes every session
↳Maintain persistent, cross-session memory for MCP-capable agents
↳Share memory between different agents or devices via a portable .db file
FAQ

FAQ

What is the difference between AgentRecall-MCP and remindb?
Both AgentRecall-MCP and remindb are in the Memory & Context category. AgentRecall-MCP has 371 stars, while remindb has 129 stars.
Which is better, AgentRecall-MCP or remindb?
The best choice depends on your use case. Choose AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.), and remindb if Prevent coding agents from re-reading the same notes every session.
Is AgentRecall-MCP free or open source?
Yes, AgentRecall-MCP is open source on GitHub (MIT).
Is remindb free or open source?
Yes, remindb is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to AgentRecall-MCP →Alternatives to remindb →AgentRecall-MCP details →remindb details →